open-source coding agents

A developer known as thedotmack has released claude-mem, an open-source tool that gives AI coding agents persistent memory across sessions. It records what an agent does, compresses it with AI, and reinjects relevant context into future sessions. The tool works with Claude Code, Codex, Gemini, Copilot, OpenCode and other agents, and has quickly drawn attention on GitHub, where developers are discussing memory as a key missing piece in agent workflows.

Developer Paul Bakaus has released 'impeccable', an open-source JavaScript project described as a design language that makes AI coding harnesses better at design. The repository provides guidance that developers can feed to AI agents so the interfaces and UI they generate follow stronger design principles. It is gaining attention among developers experimenting with AI-assisted front-end work.

A new open-source tool called Graphene has been introduced, positioning itself as a data analysis toolkit designed for use with coding agents. It was shared on Hacker News, where it quickly drew attention and discussion from developers. The project is available on GitHub, letting users inspect the code and try it with their own agent workflows.

A developer has released an open-source Python skill called i-have-adhd that stops AI coding agents from burying their answers in long explanations. The tool reformats the agent's output so the key answer comes first, cutting down on verbose responses. People are sharing it as a simple accessibility tweak that makes AI pair-programming easier for users who struggle with attention or information overload.

Trigger.dev has introduced Plimsoll, an open-source Python sandbox that lets AI agents safely execute code while analysing data. Agents often need to run calculations, inspect files, or test snippets, and the sandbox provides an isolated environment for that. Developers in the open-source community are sharing the tool as a practical addition to agent-building workflows.